We provide a brief, and inevitably incomplete overview of the use of Machine Learning (ML) and other AI methods in astronomy, astrophysics, and cosmology. Astronomy entered the big data era with the first digital sky surveys in the early 1990s and the resulting Terascale data sets, which required automating of many data processing and analysis tasks, for example the star-galaxy separation, with billions of feature vectors in hundreds of dimensions. The exponential data growth continued, with the rise of synoptic sky surveys and the Time Domain Astronomy, with the resulting Petascale data streams and the need for a real-time processing, classification, and decision making. A broad variety of classification and clustering methods have been applied for these tasks, and this remains a very active area of research. Over the past decade we have seen an exponential growth of the astronomical literature involving a variety of ML/AI applications of an ever increasing complexity and sophistication. ML and AI are now a standard part of the astronomical toolkit. As the data complexity continues to increase, we anticipate further advances leading towards a collaborative human-AI discovery.

The historical, current, and future trends in knowledge discovery from data in astronomy are presented here. The story begins with a brief history of data gathering and data organization. A description of the development ofnew information science technologies for astronomical discovery is then presented. Among these are e-Science and the virtual observatory, with its data discovery, access, display, and integration protocols; astroinformatics and data mining for exploratory data analysis, information extraction, and knowledge discovery from distributed data collections; new sky surveys' databases, including rich multivariate observational parameter sets for large numbers of objects; and the emerging discipline of data-oriented astronomical research, called astroinformatics. Astroinformatics is described as the fourth paradigm of astronomical research, following the three traditional research methodologies: observation, theory, and computation/modeling. Astroinformatics research areas include machine learning, data mining, visualization, statistics, semantic science, and scientific data management.Each of these areas is now an active research discipline, with significantscience-enabling applications in astronomy. Research challenges and sample research scenarios are presented in these areas, in addition to sample algorithms for data-oriented research. These information science technologies enable scientific knowledge discovery from the increasingly large and complex data collections in astronomy. The education and training of the modern astronomy student must consequently include skill development in these areas, whose practitioners have traditionally been limited to applied mathematicians, computer scientists, and statisticians. Modern astronomical researchers must cross these traditional discipline boundaries, thereby borrowing the best of breed methodologies from multiple disciplines. In the era of large sky surveys and numerous large telescopes, the potential for astronomical discovery is equally large, and so the data-oriented research methods, algorithms, and techniques that are presented here will enable the greatest discovery potential from the ever-growing data and information resources in astronomy.

Our work is aimed at enabling a new style of virtual, distributed scientific research. We have designed, built, and deployed an interdisciplinary virtual observatory—an online service providing access to what appears to be an integrated collection of scientific data. The Virtual Solar-Terrestrial Observatory (VSTO) is a production semantic web data framework providing access to observational data sets from fields spanning upper atmospheric terrestrial physics to solar physics. The observatory allows virtual access to a highly distributed and heterogeneous set of data that appears as if all resources are organized, stored, and retrieved or used in a common way. The end-user community includes scientists, students, and data providers. We will introduce interdisciplinary virtual observatories and their potential impact by describing our experiences with VSTO. We will also highlight some benefits of the embedded semantic web technology and also provide evaluation results after the first year of use.